简单Java爬虫

到Apache官网下载httpcomponents-client-4.4，在项目中导入jar

主要类：HttpClient，HttpGet，HttpResponse，HttpEntity

public static void getContentFromUrl(String url) {
    HttpClient client = new DefaultHttpClient();
    HttpGet getHttp = new HttpGet(url);
    while (true) {
        try {
            HttpResponse response = client.execute(getHttp);
            HttpEntity entity = response.getEntity();
            String content = null;
            String str = null;
            if (entity != null) {
                content = EntityUtils.toString(entity);
                str = new String(content.getBytes("ISO-8859-1"), "UTF-8");　　
                //在这里可以正则匹配str获得需要的信息
            }
            sleep(2000);
        } catch (IOException | InterruptedException | ParseException e) {
            e.printStackTrace();
        }
    }
}